Skip to main content


Help using calendars
Thu, May 17, '18
18:00 - 19:00
Sensing human behaviour with online data

Title: Sensing human behaviour with online data

Abstract: Our everyday usage of the Internet leaves volumes of data in its wake. Can we use this data to help us reduce delays and costs in measuring human behaviour, or even to measure behaviour we couldn’t measure before? Here, we will outline a number of studies carried out at the Data Science Lab at Warwick Business School, investigating whether online data can help us monitor disease levels, measure global travel patterns, and evaluate whether the beauty of the environment we live in might affect our health. We will discuss some of the challenges in generating estimates of human behaviour from online data when our relationship with Internet services continues to evolve at such rapid pace.


  • Suzy Moat is an Associate Professor of Behavioural Science at Warwick Business School, where she co-directs the Data Science Lab. She is also a Faculty Fellow of the Alan Turing Institute. Her research investigates whether data on our usage of the Internet, from sources such as Google, Wikipedia and Flickr, can help us measure and even predict human behaviour in the real world.
  • Tobias Preis is a Professor of Behavioural Science and Finance at the University of Warwick and a Faculty Fellow of the Alan Turing Institute.
Wed, May 23, '18
18:00 - 19:00
R package glmm: Generalised Linear Mixed Models

Christina Knudson (St Thomas) has kindly offered to speak about her new R package 'glmm' for fitting generalized linear mixed models. A version of this talk was presented at the useR!2017 conference.

Christina is associate professor of statistics at the University of St Thomas, Minnesota, and co-organizer of the R Ladies Twin Cities user group.

Conducting frequentist likelihood-based inference for generalized linear mixed models is difficult because the likelihood is a high-dimensional integral. While some R packages perform inference on an alternative function (e.g. penalized quasi likelihood), the R package glmm approximates the entire likelihood function through Monte Carlo likelihood approximation. This package conducts maximum likelihood and enables all methods of likelihood-based inference. I will give a light introduction to Monte Carlo likelihood approximation, demonstrate the use of R package glmm, describe the package's capabilities, and compare results to other packages (e.g. lme4).

Warwick R User Group logo